Rolv-Arild/replay-pretraining
Rocket League pretraining from replay files
Are you a Rocket League player or enthusiast curious about how AI can learn from human gameplay? This project helps train an AI agent to mimic human behavior in Rocket League. It takes standard Rocket League replay files as input and outputs a trained AI model capable of emulating human actions.
No commits in the last 6 months.
Use this if you want to leverage existing human gameplay data from Rocket League replays to create AI agents that behave more like players.
Not ideal if you're looking for an AI agent trained exclusively through self-play reinforcement learning, aiming for purely optimal (non-human-like) performance.
Stars
37
Forks
5
Language
Python
License
GPL-3.0
Category
Last pushed
Apr 22, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Rolv-Arild/replay-pretraining"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
LucasAlegre/sumo-rl
Reinforcement Learning environments for Traffic Signal Control with SUMO. Compatible with...
hilo-mpc/hilo-mpc
HILO-MPC is a Python toolbox for easy, flexible and fast development of...
reiniscimurs/DRL-robot-navigation
Deep Reinforcement Learning for mobile robot navigation in ROS Gazebo simulator. Using Twin...
kyegomez/RoboCAT
Implementation of Deepmind's RoboCat: "Self-Improving Foundation Agent for Robotic Manipulation"...
cbfinn/gps
Guided Policy Search